def test_upper_only(self):
# query[i] always matches target[i] so x[i] will always contain i
x = search.threshold_tanimoto_search_arena(fps, fps, 0.9)
x = list(x)
# This only processes the upper-triangle, and not the diagonal
y = search.threshold_tanimoto_search_symmetric(fps, 0.9, include_lower_triangle=False)
rows = list(row.get_indices_and_scores() for row in y)
row_sizes = map(len, rows)
# Move elements to the lower triangle
for rowno, (row, row_size) in enumerate(zip(rows, row_sizes)):
for (colno, score) in row[:row_size]:
assert colno > rowno, (rowno, colno)
rows[colno].append( (rowno, score) )
# Fill in the diagonal
row.append((rowno, 1.0))
# Put into a consistent order
row.sort()
# Match with the NxM algorithm
expected_row = x[rowno]
expected_row.reorder("increasing-index")
self.assertEquals(row, list(expected_row), rowno)
def test_upper_only(self):
# query[i] always matches target[i] so x[i] will always contain i
x = search.threshold_tanimoto_search_arena(fps, fps, 0.9)
x = list(x)
# This only processes the upper-triangle, and not the diagonal
y = search.threshold_tanimoto_search_symmetric(
fps, 0.9, include_lower_triangle=False)
rows = list(row.get_indices_and_scores() for row in y)
row_sizes = map(len, rows)
# Move elements to the lower triangle
for rowno, (row, row_size) in enumerate(zip(rows, row_sizes)):
for (colno, score) in row[:row_size]:
assert colno > rowno, (rowno, colno)
rows[colno].append((rowno, score))
# Fill in the diagonal
row.append((rowno, 1.0))
# Put into a consistent order
row.sort()
# Match with the NxM algorithm
expected_row = x[rowno]
expected_row.reorder("increasing-index")
self.assertEquals(row, list(expected_row), rowno)
def test_upper_and_lower(self):
# query[i] always matches target[i] so x[i] will always contain i
x = search.threshold_tanimoto_search_arena(fps, fps, 0.9)
# This only processes the upper-triangle, and not the diagonal
y = search.threshold_tanimoto_search_symmetric(fps, 0.9)
for i, (x_row, y_row) in enumerate(zip(x, y)):
x_row = x_row.get_indices_and_scores()
y_row = y_row.get_indices_and_scores()
y_row.append((i, 1.0))
x_row.sort()
y_row.sort()
self.assertEquals(x_row, y_row)
def test_upper_and_lower(self):
# query[i] always matches target[i] so x[i] will always contain i
x = search.threshold_tanimoto_search_arena(fps, fps, 0.9)
# This only processes the upper-triangle, and not the diagonal
y = search.threshold_tanimoto_search_symmetric(fps, 0.9)
for i, (x_row, y_row) in enumerate(zip(x, y)):
x_row = x_row.get_indices_and_scores()
y_row = y_row.get_indices_and_scores()
y_row.append((i, 1.0))
x_row.sort()
y_row.sort()
self.assertEquals(x_row, y_row)
def threshold_tanimoto_search_arena(self, queries, threshold=0.7, arena_size=100):
"""Find the fingerprints which are similar to each of the query fingerprints
DEPRECATED: Use `chemfp.search.threshold_tanimoto_search_arena`_
or `chemfp.search.threshold_tanimoto_search_symmetric`_ instead.
For each fingerprint in the `query_arena`, find all of the
fingerprints in this arena which are at least `threshold`
similar. The hits are returned as a `SearchResults` instance.
:param query_arena: query arena
:type query_arena: FingerprintArena
:param threshold: minimum similarity threshold (default: 0.7)
:type threshold: float between 0.0 and 1.0, inclusive
:returns: SearchResults
"""
return search.threshold_tanimoto_search_arena(queries, self, threshold)
